Cli delegation
Skill justinramos101/agent-skill-kit/skills/.experimental/cli-delegation
Battle-tested Agent Skills for coding agents — source-grounded, failure-driven heuristics that audit and design real surfaces. Install with npx skills.
npx -y skills add justinramos101/agent-skill-kit --skill cli-delegationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Delegate work to an external CLI coding agent — have Codex, Claude Code, or Cursor implement, refactor, analyze, research, or review something on its own. Triggers: 'have Codex/Claude Code/Cursor implement X', 'delegate this to a CLI agent', 'ask another agent to review my changes', 'get a second opinion from a different model', 'fan out these subtasks to parallel agents', 'Codex/cursor-agent auth or setup is failing'. Covers claude -p, codex exec/review, and cursor-agent: scope the task, pick the CLI and model (cursor-agent for cross-provider second opinions), run read-only by default, verify the output before trusting it. Do NOT use for auditing a codebase or a CLI's UX yourself, hardening a repo for coding agents, designing a new CLI/SDK, or ordinary in-session coding with no delegation or different-model signal.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.7 KB, as published. Nobody here has run it
CLI Delegation
Hand well-scoped tasks to an external CLI agent — Claude Code (claude -p),
Codex (codex exec / codex review), or Cursor (cursor-agent -p).
Core principle: every delegated result is a proposal to verify, never
truth. Delegation is encouraged: fan out parallel invocations for
independent subtasks, then verify each return yourself.
Invariants
- Verify-before-trust: never trust unreviewed delegated work — a delegated result gets used or relayed only after it's checked against local evidence.
- Volatile flags: CLI flags drift between releases — verify against
--helpat run time; the references carry gotchas, not flag tables. - Secrets: scan diffs/files for credentials before piping them out; if risk is unclear, don't pipe — surface the path and why it's suspected (never the raw value) and get explicit sign-off.
- Bound every run: turn caps (e.g.
--max-turns3–10), timeouts, fan-out width of a handful, not hundreds.
Workflow
- Scope. One objective per invocation: inputs, constraints, and the exact output wanted (a diff, findings, an answer). Brief it like a new hire — no context carries over.
- Pick the CLI + model. Claude Code for depth (
--effort highon hard reasoning); Codex for native diff review (codex review); Cursor for model diversity — its multi-provider--model(runcursor-agent --list-models; the reference lists the current options) puts a second opinion on a different model than wrote the code. Fast/cheap models for mechanical subtasks. Gotchas:references/claude-code.md,references/codex.md,references/cursor.md. - Execute read-only.
claude --permission-mode plan/codex --sandbox read-only/cursor-agent --mode plan. Widen write access only when the task must edit, explicitly and scoped; never pass a--dangerously-*/--yolo/ force bypass without the user's explicit approval. To fan out, run N invocations concurrently (&+wait), one objective each. - Verify. Reconcile every claim against local files, run tests, spot-check diffs; discard findings that contradict the actual code.
Stop conditions
- Done when delegated output is verified and reconciled — report what you accepted, rejected, or left open.
- Delegate CLI missing, unauthenticated, or untrusted: report the exact
blocker (
codex doctor/scripts/codex-doctor-check.shfor Codex); never silently fall back to another provider. - Two failed attempts on one invocation blocker → stop; report the failing command and its last error, and ask how to proceed — don't retry blind.
- Run to completion; ask only on genuine blockers (missing scope, secret risk, write access needed).